maxpagels

# Sample code for building a multi-layer perceptron
# that predicts the brightness of a light bulb based
# on the month, weekday, hour and minute.

import numpy as np

from keras.models import Sequential
from keras.layers.core import Dense, Activation
from keras.utils import np_utils
from sklearn import preprocessing

maxpagels

import numpy as np
from flask import Flask
from flask import request
from flask import jsonify


# A simple implementation of a multi-armed bandit using Thompson Sampling.

class ThompsonBandit(object):

maxpagels

import numpy as np

class ContextualThompson(object):

  def __init__(self, d=10, R=0.01, epsilon=0.5, delta=1.0, n_arms=10):
    self.n_arms = n_arms
    self.d = d
    self.R = R
    self.delta = delta
    self.epsilon = epsilon

maxpagels

import csv
import sys
import numpy

from keras.models import Sequential
from keras.layers import Dense, Activation, Embedding, TimeDistributed, RepeatVector
from keras.layers import LSTM
from keras.callbacks import ModelCheckpoint, TensorBoard
from keras.utils import to_categorical

maxpagels

""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """
import numpy as np
import cPickle as pickle
import gym

# hyperparameters
H = 200 # number of hidden layer neurons
batch_size = 10 # every how many episodes to do a param update?
learning_rate = 1e-4
gamma = 0.99 # discount factor for reward

maxpagels

# Evolution Strategies for Reinforcement Learning
# See: https://blog.openai.com/evolution-strategies/

import numpy as np
from keras.layers import Dense
from keras.models import Sequential

np.random.seed(0)
model = Sequential()
layer1 = Dense(2,input_dim=5)

maxpagels

# Skeleton pseudocode for implementation of Evolved Policy Gradients
# Original paper: https://arxiv.org/pdf/1802.04821.pdf

import numpy as np

lr_delta = 0.01
lr_alpha = 0.01
noise_stddev = 0.5
K = 10
discount_factor = 0.5

maxpagels

import numpy as np
from sklearn import linear_model

n_samples, n_features = 1, 500
y = np.random.randn(n_samples)
X = np.random.randn(n_samples, n_features)
clf = linear_model.SGDRegressor()

import time

maxpagels

import math
import types
from pandas.api.types import is_string_dtype
from pandas.api.types import is_numeric_dtype
from tqdm import tqdm


def df_to_vw_regression(df, filepath='in.txt', sample_weights=None, columns=None, target=None, namespace='namespace'):
    if columns is None:
        columns = df.columns.tolist()

maxpagels

# Python implementation of the EXP3 (Exponential weight for Exploration and Exploitation)
# algorithm for solving adversarial bandit problems. Based on the original paper:
# http://rob.schapire.net/papers/AuerCeFrSc01.pdf

import numpy as np
import time

np.random.seed(12345)

n_arms = 4